url: https://docs.robwiederstein.org/baflakehouse

template:
  bootstrap: 5
  bootswatch: flatly

navbar:
  structure:
    left: [intro, reference, articles, presentation]
  components:
    presentation:
      text: "Slides"
      icon: fa-person-chalkboard
      href: slides/index.html

reference:
  - title: "Data Ingestion & Lakehouse Setup"
    desc: "Functions for moving raw CSV data into the MinIO Lakehouse as partitioned Parquet."
    contents:
      - baflakehouse-package
      - convert_to_parquet
      - connect_baf
      - clean_baf_base

  - title: "Feature Engineering & Preprocessing"
    desc: "Recipes and transformations applied across the pipeline layers."
    contents:
      - engineer_features
      - generate_model_inputs
      - build_eda_recipe
      - build_baf_recipe

  - title: "Exploratory Data Analysis"
    desc: "Diagnostic model and visualizations for understanding the fraud signal."
    contents:
      - train_diag_model
      - plot_var_imp
      - plot_hexbin_interaction
      - plot_missingness
      - plot_num_cor

  - title: "Model Selection & Tuning"
    desc: "Imbalance strategy tournament, hyperparameter tuning, and results formatting."
    contents:
      - run_imbalance_tournament
      - tune_lgbm
      - format_tournament_gt
      - plot_efficiency

  - title: "Final Evaluation & Production Deployment"
    desc: "Holdout evaluation on months 6-7 and MinIO model artifact serialization."
    contents:
      - evaluate_final_model
      - train_production_model

  - title: "Reporting"
    desc: "Figures, tables, and slide rendering for the Quarto presentation."
    contents:
      - plot_fraud_by_month
      - plot_conf_mat_heatmap
      - compute_fraud_by_month
      - format_fraud_by_month_gt
      - save_report_figure
      - save_report_table
      - render_slides